Face Detection Method in Surveillance Systems Using Haar Feature and Deep Neural Network

Face detection is one of the most widespread applications in the modern world society. Tremendous strides have been made to improve the performance of face detection, however, accuracy and efficiency of face localization in the wild remains an open challenge. This paper presents an efficient method for face detection in a surveillance system. The proposed method combines traditional computer vision method and modern technique. The method has been experimented under several datasets to evaluate the accuracy and efficiency of face localization. The result achieves 96.66% and 26.85 frame per second.